writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is writing-skills in obra/superpowers

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, well-validated TDD-adapted workflow and many concrete templates. Its main weaknesses are verbosity/redundancy and progressive disclosure: it is a monolithic file that violates its own token-efficiency guidance and references bundle files that are not present.

Suggestions

Split the long testing methodology and SDO deep-dive into actual reference files (the referenced testing-skills-with-subagents.md, persuasion-principles.md, anthropic-best-practices.md, graphviz-conventions.dot, render-graphs.js do not exist in the bundle) and verify every "See X" link resolves to a real file.

Collapse the redundant test-first messaging: "The Iron Law", "Common Rationalizations for Skipping Testing", "STOP: Before Moving to Next Skill", and "The Bottom Line" restate the same point — consolidate into one section to approach the skill's own <500-word target.

Trim repeated good/bad example pairs (the SDO section alone has four YAML blocks making the same workflow-summary point) to reduce token cost while keeping one strong illustration per point.

Dimension	Reasoning	Score
Conciseness	At ~690 lines the body is mostly high-value guidance rather than explaining concepts Claude already knows, but it repeats the same TDD/test-first message across "The Iron Law", "Common Rationalizations", "STOP: Before Moving to Next Skill", and "The Bottom Line", and could be tightened.	3 / 5
Actionability	Provides copy-paste-ready templates (frontmatter, rationalization table, red flags list, directory structures) plus concrete good/bad YAML and code examples that cover the common authoring cases.	5 / 5
Workflow Clarity	The RED-GREEN-REFACTOR sequence is clearly staged with explicit validation checkpoints (run baseline, verify compliance, micro-test with 5+ reps), feedback loops (refactor to close loopholes, re-test), and a mandatory per-skill checklist.	5 / 5
Progressive Disclosure	Section structure is clear and references are explicitly signaled (e.g. "See persuasion-principles.md", "See testing-skills-with-subagents.md"), but no bundle files exist so those references are broken, and the monolithic ~690-line body inlines content (long testing methodology, SDO deep-dive) that the skill's own guidance says belongs in separate files.	3 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, trigger-focused, and clearly scopes the skill to authoring/editing/verifying skills. It cleanly answers both what and when without workflow summary, consistent with the skill's own SDO guidance.

Dimension	Reasoning	Score
Specificity	Names the domain (skills) and three concrete actions — "creating new skills, editing existing skills, or verifying skills work before deployment" — which lists several specific actions with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (create/edit/verify skills) and when ("Use when...") with concrete trigger phrases, matching the anchor that requires both answered clearly.	5 / 5
Trigger Term Quality	Natural terms a user would say are present ("creating new skills", "editing existing skills", "verifying skills", "deployment"), though a few common synonyms like "authoring" or "writing skills" are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (skill authoring/verification) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (690 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/writing-skills/SKILL.md
Commit: 99fd749

Reviewed: 34 minutes ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.